Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 3B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 128k |
| These models have no shared benchmark scores. | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 61.6% | — |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | — | 77.4% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 51.7% |
| Overview | ||
| Company | Mistral | Mistral |
| Release date | Jul 10 2025 | Oct 16 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Devstral MediumvsClaude Fable 5.2Ministral 3BvsClaude Fable 5.2Devstral MediumvsGPT-6.2 AstraMinistral 3BvsGPT-6.2 AstraDevstral MediumvsGemini 4 HydrogenMinistral 3BvsGemini 4 HydrogenDevstral MediumvsMuse EmberMinistral 3BvsMuse EmberDevstral MediumvsGrok 4.7Ministral 3BvsGrok 4.7Devstral MediumvsDeepSeek-V4.1-Flash-1017Ministral 3BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Devstral Medium and Ministral 3B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Ministral 3B shipped 267 days before Devstral Medium, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (Devstral Medium) vs 128k (Ministral 3B).
Direct benchmark comparisons are unavailable — Devstral Medium and Ministral 3B don't publish scores on any of the same benchmarks.